© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 3504
    Prev
    Next
    INDEX
    Explanations

    instances of physical actions and states, particularly those involving transitions, movement, and time-related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    CloseOperation
    -0.40
    MessageState
    -0.40
     jLabel
    -0.34
    SequentialGroup
    -0.30
     exited
    -0.30
    makeText
    -0.29
    InstrumentedTest
    -0.28
    createCanvas
    -0.28
    ContentAsync
    -0.28
    FieldBuilder
    -0.28
    POSITIVE LOGITS
    进来
    0.96
     masuk
    0.85
    进去
    0.82
    เข้า
    0.82
    進去
    0.77
     inwards
    0.76
     inward
    0.72
    进
    0.71
    入
    0.71
     dedans
    0.65
    Activations Density 0.406%

    No Known Activations